Carrier determination method and device, electronic equipment and storage medium

By using a gradient-boosting decision tree model to predict carrier performance, the problem of carrier selection failing to meet service requirements is solved, achieving reasonable allocation of carrier resources and meeting service needs, thus providing a stable and efficient data transmission experience.

CN121099433APending Publication Date: 2025-12-09CHINA UNITED NETWORK COMM GRP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202511453235.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-10-11
Publication Date
2025-12-09

AI Technical Summary

Technical Problem

Existing carrier selection methods cannot meet users' service needs, especially in high- and low-frequency carrier aggregation, where they cannot intelligently select appropriate carriers to meet the differentiated experience of different services.

Method used

By determining the type of service data of the terminal, a pre-trained gradient boosting decision tree model is used to predict the transmission performance of different frequency carriers based on terminal state parameters and network performance parameters, and the target carrier is dynamically selected to meet service requirements.

Benefits of technology

It enables intelligent carrier selection, ensuring more rational allocation of carrier resources, meeting the quality of service requirements of different services, avoiding resource waste, and providing a stable and efficient data transmission experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121099433A_ABST
    Figure CN121099433A_ABST
Patent Text Reader

Abstract

The invention provides a carrier determination method and device, electronic equipment and a storage medium, and relates to the field of mobile communication. The method comprises the following steps: determining a target service type corresponding to service data of a terminal; determining a first prediction result based on the terminal state parameter and the network performance parameter of the first carrier, the first prediction result being used for indicating the transmission performance which can be reached when the first carrier transmits the service data of the target service type; determining a second prediction result based on the terminal state parameter and the network performance parameter of the second carrier, the second prediction result being used for indicating the transmission performance which can be reached when the second carrier transmits the service data of the target service type; and determining a target carrier from the first carrier and the second carrier based on the first prediction result and the second prediction result. According to the invention, carrier selection is carried out according to the transmission performance which can be achieved when different carriers transmit the service data of the target service type, so that the selected target carrier can meet the service requirements.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of mobile communications, and more particularly to a carrier determination method, apparatus, electronic device, and storage medium. Background Technology

[0002] In carrier aggregation, inter-band aggregation is achieved by aggregating high-frequency carriers and low-frequency carriers.

[0003] Currently, carrier selection is typically assisted by setting a reference signal receiving power (RSRP) threshold. However, carriers selected in this way may not meet the current service requirements of users. Summary of the Invention

[0004] This application provides a carrier determination method, apparatus, electronic device, and storage medium that can meet the user's business needs.

[0005] To achieve the above objectives, this application adopts the following technical solution: In a first aspect, this application provides a carrier determination method, the method comprising: determining a target service type corresponding to service data of a terminal; determining a first prediction result based on terminal state parameters and network performance parameters of a first carrier, wherein the terminal state parameters are used to indicate the channel state and mobility state of the terminal, and the first prediction result is used to indicate the transmission performance that can be achieved when the target service type service data is transmitted on the first carrier; determining a second prediction result based on the terminal state parameters and network performance parameters of a second carrier, wherein the second prediction result is used to indicate the transmission performance that can be achieved when the target service type service data is transmitted on the second carrier; and determining a target carrier from the first carrier and the second carrier based on the first prediction result and the second prediction result; wherein the frequency of the first carrier is different from the frequency of the second carrier.

[0006] In conjunction with the first aspect above, in one possible implementation, determining the target service type corresponding to the terminal's service data includes: when the service data is transmitted encrypted, detecting the similarity between the traffic feature parameters and standard traffic feature parameters in a knowledge base based on the traffic feature parameters of the service data; wherein the knowledge base is used to store at least one standard service template, the standard service template including a standard service type, and a standard service category, standard service subcategory, standard traffic feature parameters, and standard transmission performance parameters corresponding to the standard service type; if there are standard traffic feature parameters in the knowledge base whose similarity meets the threshold condition, the standard service type corresponding to the standard traffic feature parameters is determined as the target service type.

[0007] In conjunction with the first aspect above, in one possible implementation, determining the target service type corresponding to the terminal's service data includes: in response to plaintext transmission of service data, determining the target service type corresponding to the terminal's service data through Deep Packet Inspection (DPI) technology.

[0008] In conjunction with the first aspect above, in one possible implementation, determining the target carrier from the first carrier and the second carrier based on the first prediction result and the second prediction result includes: determining the target carrier from the first carrier and the second carrier based on the first prediction result, the second prediction result, and the standard transmission performance parameters corresponding to the target service type.

[0009] In conjunction with the first aspect above, in one possible implementation, either the first prediction result or the second prediction result includes uplink transmission rate, downlink transmission rate, latency, and reliability; the standard transmission performance parameters include standard uplink transmission rate, standard downlink transmission rate, standard latency, and standard reliability; determining the target carrier from the first carrier and the second carrier based on the first prediction result, the second prediction result, and the standard transmission performance parameters corresponding to the target service type includes: in response to both the first prediction result and the second prediction result meeting the service requirement condition, determining the target carrier from the first carrier and the second carrier based on the satisfaction score of the first carrier and the satisfaction score of the second carrier, wherein the satisfaction score of the first carrier is used to indicate the first prediction result. The degree of conformity between the second prediction result and the standard transmission performance parameters, the satisfaction score of the second carrier is used to indicate the degree of conformity between the second prediction result and the standard transmission performance parameters; in response to the first prediction result or the second prediction result meeting the service requirement conditions, the carrier that meets the service requirement conditions among the first carrier and the second carrier is determined as the target carrier; in response to the first prediction result and the second prediction result not meeting the service requirement conditions, the first carrier and the second carrier are determined as the target carrier; the service requirement conditions include that the uplink transmission rate of the prediction result is greater than or equal to the standard uplink transmission rate, and the downlink transmission rate of the prediction result is greater than or equal to the standard downlink transmission rate, and the delay of the prediction result is less than or equal to the standard delay, and the reliability of the prediction result is greater than or equal to the standard reliability.

[0010] In conjunction with the first aspect above, in one possible implementation, determining a target carrier from the first carrier and the second carrier based on the satisfaction score of the first carrier and the satisfaction score of the second carrier includes: determining the first carrier as the target carrier in response to the satisfaction score of the first carrier being greater than or equal to the satisfaction score of the second carrier; and determining the second carrier as the target carrier in response to the satisfaction score of the first carrier being less than the satisfaction score of the second carrier.

[0011] In conjunction with the first aspect above, in one possible implementation, the process of determining the satisfaction score of the first carrier includes: determining a first score for the first carrier based on the uplink transmission rate of the first prediction result and the standard uplink transmission rate of the standard transmission performance parameters, wherein the first score of the first carrier is used to characterize the degree of conformity between the uplink transmission rate of the first carrier and the standard uplink transmission rate of the standard transmission performance parameters; and determining a second score for the first carrier based on the downlink transmission rate of the first prediction result and the standard downlink transmission rate of the standard transmission performance parameters, wherein the second score of the first carrier is used to characterize the degree of conformity between the downlink transmission rate of the first carrier and the standard downlink transmission rate of the standard transmission performance parameters. The degree of conformity is determined as follows: Based on the standard delay of the standard transmission performance parameters and the delay of the first prediction result, a third score of the first carrier is determined, which characterizes the degree of conformity between the delay of the first carrier and the standard delay of the standard transmission performance parameters; Based on the reliability of the first prediction result and the standard reliability of the standard transmission performance parameters, a fourth score of the first carrier is determined, which characterizes the degree of conformity between the reliability of the first carrier and the standard reliability of the standard transmission performance parameters; Based on the first score, the second score, the third score, and the fourth score of the first carrier, a satisfaction score of the first carrier is determined.

[0012] In conjunction with the first aspect above, in one possible implementation, the process of determining the satisfaction score of the second carrier includes: determining a first score for the second carrier based on the uplink transmission rate of the second prediction result and the standard uplink transmission rate of the standard transmission performance parameters, wherein the first score of the second carrier is used to characterize the degree of conformity between the uplink transmission rate of the second carrier and the standard uplink transmission rate of the standard transmission performance parameters; and determining a second score for the second carrier based on the downlink transmission rate of the second prediction result and the standard downlink transmission rate of the standard transmission performance parameters, wherein the second score of the second carrier is used to characterize the degree of conformity between the downlink transmission rate of the second carrier and the standard downlink transmission rate of the standard transmission performance parameters. The degree of conformity between the second carrier and the standard delay of the standard transmission performance parameters is determined; based on the standard delay of the standard transmission performance parameters and the delay of the second prediction result, the third score of the second carrier is determined, which is used to characterize the degree of conformity between the delay of the second carrier and the standard delay of the standard transmission performance parameters; based on the reliability of the second prediction result and the standard reliability of the standard transmission performance parameters, the fourth score of the second carrier is determined, which is used to characterize the degree of conformity between the reliability of the second carrier and the standard reliability of the standard transmission performance parameters; based on the first score, the second score, the third score, and the fourth score of the second carrier, the satisfaction score of the second carrier is determined.

[0013] In conjunction with the first aspect above, in one possible implementation, determining a first prediction result based on terminal state parameters and network performance parameters of the first carrier includes: processing the terminal state parameters and network performance parameters of the first carrier using a pre-trained first gradient boosting decision tree (GSDT) model to obtain the first prediction result; determining a second prediction result based on terminal state parameters and network performance parameters of the second carrier includes: processing the terminal state parameters and network performance parameters of the second carrier using a pre-trained second gradient boosting decision tree (GSDT) model to obtain the second prediction result.

[0014] Secondly, this application provides a carrier determination apparatus, comprising: a first determination unit for determining a target service type corresponding to service data of a terminal; a second determination unit for determining a first prediction result based on terminal state parameters and network performance parameters of a first carrier, wherein the terminal state parameters indicate the channel state and mobility state of the terminal, and the first prediction result indicates the transmission performance achievable when transmitting service data of the target service type on the first carrier; a third determination unit for determining a second prediction result based on the terminal state parameters and network performance parameters of a second carrier, wherein the second prediction result indicates the transmission performance achievable when transmitting service data of the target service type on the second carrier; and a fourth determination unit for determining a target carrier from the first carrier and the second carrier based on the first prediction result and the second prediction result; wherein the frequency of the first carrier is different from the frequency of the second carrier.

[0015] In conjunction with the second aspect above, in one possible implementation, the first determining unit is used to: in the case of encrypted transmission of business data, detect the similarity between the traffic feature parameters and standard traffic feature parameters in the knowledge base based on the traffic feature parameters of the business data; wherein, the knowledge base is used to store at least one standard business template, the standard business template including a standard business type, and a standard business category, a standard business subcategory, standard traffic feature parameters, and standard transmission performance parameters corresponding to the standard business type; if there are standard traffic feature parameters in the knowledge base whose similarity meets the threshold condition, the standard business type corresponding to the standard traffic feature parameter is determined as the target business type.

[0016] In conjunction with the second aspect above, in one possible implementation, the first determining unit is used to: in response to the plaintext transmission of service data, determine the target service type corresponding to the terminal's service data through deep packet inspection (DPI) technology.

[0017] In conjunction with the second aspect above, in one possible implementation, the fourth determining unit is used to: determine the target carrier from the first carrier and the second carrier based on the first prediction result, the second prediction result, and the standard transmission performance parameters corresponding to the target service type.

[0018] In conjunction with the second aspect above, in one possible implementation, either the first prediction result or the second prediction result includes uplink transmission rate, downlink transmission rate, latency, and reliability; the standard transmission performance parameters include standard uplink transmission rate, standard downlink transmission rate, standard latency, and standard reliability; the fourth determining unit is configured to: in response to the condition that both the first prediction result and the second prediction result meet the service requirement, determine the target carrier from the first carrier and the second carrier based on the satisfaction score of the first carrier and the satisfaction score of the second carrier, wherein the satisfaction score of the first carrier is used to indicate the degree of conformity between the first prediction result and the standard transmission performance parameters, and the satisfaction score of the second carrier... The score is used to indicate the degree of conformity between the second prediction result and the standard transmission performance parameters; in response to the first prediction result or the second prediction result meeting the service requirement conditions, the carrier that meets the service requirement conditions among the first carrier and the second carrier is determined as the target carrier; in response to the first prediction result and the second prediction result not meeting the service requirement conditions, the first carrier and the second carrier are determined as the target carrier; the service requirement conditions include that the uplink transmission rate of the prediction result is greater than or equal to the standard uplink transmission rate, and the downlink transmission rate of the prediction result is greater than or equal to the standard downlink transmission rate, and the delay of the prediction result is less than or equal to the standard delay, and the reliability of the prediction result is greater than or equal to the standard reliability.

[0019] In conjunction with the second aspect above, in one possible implementation, the fourth determining unit is used to: determine the first carrier as the target carrier in response to the satisfaction score of the first carrier being greater than or equal to the satisfaction score of the second carrier; and determine the second carrier as the target carrier in response to the satisfaction score of the first carrier being less than the satisfaction score of the second carrier.

[0020] In conjunction with the second aspect above, in one possible implementation, the fourth determining unit is configured to: determine a first score for the first carrier based on the uplink transmission rate of the first prediction result and the standard uplink transmission rate of the standard transmission performance parameters, wherein the first score of the first carrier characterizes the degree of conformity between the uplink transmission rate of the first carrier and the standard uplink transmission rate of the standard transmission performance parameters; determine a second score for the first carrier based on the downlink transmission rate of the first prediction result and the standard downlink transmission rate of the standard transmission performance parameters, wherein the second score of the first carrier characterizes the degree of conformity between the downlink transmission rate of the first carrier and the standard downlink transmission rate of the standard transmission performance parameters; determine a third score for the first carrier based on the standard delay of the standard transmission performance parameters and the delay of the first prediction result, wherein the third score of the first carrier characterizes the degree of conformity between the delay of the first carrier and the standard delay of the standard transmission performance parameters; determine a fourth score for the first carrier based on the reliability of the first prediction result and the standard reliability of the standard transmission performance parameters, wherein the fourth score of the first carrier characterizes the degree of conformity between the reliability of the first carrier and the standard reliability of the standard transmission performance parameters; and determine a satisfaction score for the first carrier based on the first score, the second score, the third score, and the fourth score of the first carrier.

[0021] In conjunction with the second aspect above, in one possible implementation, the fourth determining unit is configured to: determine a first score for the second carrier based on the uplink transmission rate of the second prediction result and the standard uplink transmission rate of the standard transmission performance parameters, wherein the first score of the second carrier characterizes the degree of conformity between the uplink transmission rate of the second carrier and the standard uplink transmission rate of the standard transmission performance parameters; determine a second score for the second carrier based on the downlink transmission rate of the second prediction result and the standard downlink transmission rate of the standard transmission performance parameters, wherein the second score of the second carrier characterizes the degree of conformity between the downlink transmission rate of the second carrier and the standard downlink transmission rate of the standard transmission performance parameters; determine a third score for the second carrier based on the standard delay of the standard transmission performance parameters and the delay of the second prediction result, wherein the third score of the second carrier characterizes the degree of conformity between the delay of the second carrier and the standard delay of the standard transmission performance parameters; determine a fourth score for the second carrier based on the reliability of the second prediction result and the standard reliability of the standard transmission performance parameters, wherein the fourth score of the second carrier characterizes the degree of conformity between the reliability of the second carrier and the standard reliability of the standard transmission performance parameters; and determine a satisfaction score for the second carrier based on the first score, the second score, the third score, and the fourth score of the second carrier.

[0022] In conjunction with the second aspect above, in one possible implementation, the second determining unit is used to: process the terminal state parameters and the network performance parameters of the first carrier through a pre-trained first gradient boosting decision tree (GSDT) model to obtain a first prediction result; the third determining unit is used to: process the terminal state parameters and the network performance parameters of the second carrier through a pre-trained second gradient boosting decision tree (GSDT) model to obtain a second prediction result.

[0023] Thirdly, this application provides an electronic device, including: a processor and a communication interface; the communication interface and the processor are coupled, and the processor is used to run computer programs or instructions to implement the carrier determination method as described in the first aspect and any possible implementation of the first aspect.

[0024] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the carrier determination method as described in the first aspect and any possible implementation thereof.

[0025] Fifthly, this application provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the carrier determination method as described in the first aspect and any possible implementation thereof.

[0026] In a sixth aspect, this application provides a chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being configured to run computer programs or instructions to implement the carrier determination method as described in the first aspect and any possible implementation thereof.

[0027] Specifically, the chip provided in this application also includes a memory for storing computer programs or instructions.

[0028] It should be noted that the aforementioned computer instructions may be stored, in whole or in part, on a computer-readable storage medium. This computer-readable storage medium may be packaged together with the processor of the device, or it may be packaged separately from the processor of the device; this application does not impose any limitation on this.

[0029] In a seventh aspect, this application provides a carrier determination system, comprising: a terminal and a carrier determination device, wherein the carrier determination device is configured to perform the carrier determination method as described in the first aspect and any possible implementation thereof.

[0030] The descriptions of aspects two through seven in this application can be referenced to the detailed description of aspect one; and the beneficial effects of the descriptions of aspects two through seven can be referenced to the analysis of the beneficial effects of aspect one, which will not be repeated here.

[0031] In this application, the name of the aforementioned carrier determination device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear under other names. As long as the function of each device or functional module is similar to that of this application, it falls within the scope of the claims of this application and its equivalents.

[0032] These or other aspects of this application will become more readily apparent in the following description.

[0033] The carrier determination method provided in this application obtains a first prediction result, i.e., the transmission performance that the first carrier can achieve when transmitting service data of the target service type, using terminal state parameters and network performance parameters of the first carrier. Furthermore, it obtains a second prediction result, i.e., the transmission performance that the second carrier can achieve when transmitting service data of the target service type, using terminal state parameters and network performance parameters of the second carrier. By fully utilizing parameter information from both the terminal and network sides, the prediction results for carriers of different frequencies are determined, making the prediction results more consistent with the actual usage of the current carrier. Carrier selection is performed based on the prediction results of different carriers, ensuring that the selected target carrier better meets the service requirements of the target service type. Attached Figure Description

[0034] Figure 1 A flowchart of a carrier determination method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the module division of a carrier determination system provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a carrier determination device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the hardware structure of a carrier determination device provided in an embodiment of this application. Detailed Implementation

[0035] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0036] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0037] The terms "first" and "second," etc., used in the specification and drawings of this application are used to distinguish different objects or to distinguish different treatments of the same object, rather than to describe a specific order of objects.

[0038] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.

[0039] It should be noted that in the embodiments of this application, the words "exemplarily" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplarily" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplarily" or "for example" is intended to present the relevant concepts in a specific manner.

[0040] In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0041] Carrier aggregation (CA) is a key technology in communication systems that can be used to increase transmission bandwidth. This technology effectively enhances bandwidth by aggregating two or more component carriers (CCs), thereby significantly increasing uplink and downlink transmission rates.

[0042] Carrier aggregation consists of a primary component carrier (PCC) and at least one secondary component carrier (SCC). Currently, in practical applications of carrier aggregation, low-frequency carriers are typically chosen as the primary carrier for transmitting signaling and data. In communication systems, secondary carriers are added to transmit data based on a certain reference signal receiving power (RSRP) threshold. Taking 3.5GHz and 900MHz carrier aggregation as an example, carrier aggregation is only initiated when the terminal is camped on the 900MHz band. For example, the secondary carrier addition threshold is set to -115dBm, and the secondary carrier deconfiguration threshold is set to -120dBm. When the secondary carrier RSRP is higher than -115dBm, the secondary carrier is added; when the secondary carrier RSRP is lower than -120dBm, the secondary carrier is configured. Simultaneously, an activation packet size threshold is set for cases requiring carrier aggregation configuration; when the data packet exceeds this threshold, carrier aggregation is activated. Downlink data from the same terminal can be split into two parts by the base station and transmitted in parallel through the primary and secondary carriers, thereby improving the overall throughput.

[0043] In carrier aggregation, the aggregated member carriers can be carriers in the same frequency band (i.e., intra-band aggregation) or carriers in different frequency bands (i.e., inter-band aggregation).

[0044] High- and low-frequency carrier aggregation is a key technology in carrier aggregation, belonging to inter-band aggregation. It can simultaneously utilize spectrum resources in both low- and high-frequency bands, balancing coverage, network capacity, and user experience. High- and low-frequency carrier aggregation is a specific application form of carrier aggregation.

[0045] Low-frequency (LFF) and high-frequency (HF) carriers each have their own unique advantages and disadvantages. LFF carriers offer advantages such as low propagation loss, strong diffraction capability, wide coverage, and good penetration through buildings, making them ideal for providing wide-area and deep coverage. However, LFF carriers also have limitations; their available continuous bandwidth is typically narrow, resulting in limited peak rates per carrier. For example, a typical LFF carrier band might be an 11MHz continuous bandwidth within a 900MHz center frequency band. Typical LFF carrier bands include Sub-1GHz (e.g., 700MHz, 800MHz, 900MHz) and 1GHz-2GHz (e.g., 1800MHz, 2100MHz). HF carriers, on the other hand, offer abundant available spectrum resources, large continuous bandwidth, and can provide users with extremely high peak rates per user and network capacity. For example, typical HF carrier bands are 100MHz, 200MHz, or even higher. However, HF carriers suffer from high propagation loss, poor diffraction capability, small coverage, susceptibility to obstructions (such as buildings, foliage, etc.), and weak penetration. Common high-frequency carrier bands include C-band (e.g., around 3.5 GHz) and millimeter-wave bands (e.g., 24 GHz, 28 GHz, 39 GHz, etc.).

[0046] In practical applications, low-frequency carriers and high-frequency carriers play different roles. Low-frequency carriers generally serve as "anchors" or "base layers," providing broad and reliable basic connectivity and coverage to ensure users have basic access and meet mobility management requirements such as control signaling, voice, and data transmission. High-frequency carriers, on the other hand, act as "capacity layers" or "accelerators." When users are in areas with good high-frequency carrier coverage (such as hotspot areas or indoor locations near base stations), the system dynamically aggregates high-frequency carriers to provide users with ultra-high-speed data transmission services. Through the synergistic effect of high-frequency and low-frequency carriers, users can enjoy more stable and seamless coverage while moving, and experience extremely high peak rates and capacity in hotspot areas, achieving an optimal balance between coverage and capacity.

[0047] While low-frequency carriers offer stable and continuous coverage, enabling reliable transmission of signaling and data, and high-frequency carriers are used for data transmission due to their large bandwidth, current high- and low-frequency carrier aggregation does not fully consider the needs of different services and cannot intelligently select appropriate carriers. This may result in some services failing to meet actual service quality requirements.

[0048] For example, with the continuous development of communication technology, current services are becoming increasingly diverse, encompassing not only traditional Hypertext Transfer Protocol (HTTP), Voice Over Internet Protocol (VoIP), Internet of Things (IoT), video, gaming, and payment-related QR code services, but also a variety of emerging services such as integrated sensing and intelligent uplink. Against this backdrop, how to intelligently schedule the transmission of user data on low-frequency and high-frequency carriers to ensure a differentiated user experience across various services has become a crucial research topic.

[0049] Therefore, the carrier determination method provided in this application obtains a first prediction result, i.e., the transmission performance that the first carrier can achieve when transmitting service data of the target service type, by using terminal state parameters and network performance parameters of the first carrier. Furthermore, it obtains a second prediction result, i.e., the transmission performance that the second carrier can achieve when transmitting service data of the target service type, by using terminal state parameters and network performance parameters of the second carrier. By fully utilizing parameter information from both the terminal and network sides, the prediction results for carriers of different frequencies are determined, making the prediction results more consistent with the actual usage of the current carrier. Carrier selection is performed based on the prediction results of different carriers, ensuring that the selected target carrier better meets the service requirements of the target service type.

[0050] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0051] It should be noted that the various embodiments of this application can be referenced or learned from each other. For example, the same or similar steps, method embodiments, system embodiments and device embodiments can be referenced from each other without limitation.

[0052] Figure 1 This is a flowchart illustrating a carrier determination method provided in an embodiment of this application. Figure 1 As shown, this method can be implemented through S101 to S104.

[0053] S101. Determine the target service type corresponding to the service data of the terminal.

[0054] For example, the target service type can be the service type currently being used by the terminal. Examples include 8K video-on-demand service and industrial robotic arm control service.

[0055] S102. Determine the first prediction result based on the terminal status parameters and the network performance parameters of the first carrier.

[0056] The terminal status parameters are used to indicate the terminal's channel status and mobility status. For example, the terminal status parameters include the terminal's reference signal receiving power (RSRP), the terminal's signal to interference plus noise ratio (SINR), and the terminal's mobility speed.

[0057] For example, the network performance parameters of the first carrier include the number of radioresource control (RRC) connected users of the first carrier, the uplink physical resource block (PRB) utilization of the first carrier, the downlink PRB utilization of the first carrier, and the quality of service class identifier (QCI) of the first carrier.

[0058] Terminal status parameters reflect the signal strength of the terminal's environment and its mobility. Network performance parameters of the first carrier reflect the traffic flow and scheduling of that carrier. Both terminal status parameters and the network performance parameters of the first carrier affect uplink transmission rate, downlink transmission rate, latency, and reliability.

[0059] The first prediction result is used to indicate the transmission performance that can be achieved when transmitting service data of the target service type on the first carrier. For example, the first prediction result includes uplink transmission rate, downlink transmission rate, latency, and reliability.

[0060] In some embodiments, the terminal state parameters and the network performance parameters of the first carrier are processed by a pre-trained gradient boosting decision tree (GSDT) model to obtain a first prediction result.

[0061] For example, parameter information of the target service type during the historical usage of the first carrier is used as a sample set. For instance, historical terminal status parameters, historical network performance parameters of the first carrier, and historical transmission performance parameters of the first carrier when transmitting service data of the target service type are used as the sample set. Historical terminal status parameters include the terminal's historical RSRP, historical SINR, and historical mobility speed. Historical network performance parameters of the first carrier include the historical RRC connected users, historical PRB utilization, downlink PRB utilization, and historical QCI. Historical transmission performance parameters of the first carrier when transmitting service data of the target service type include the historical uplink transmission rate, historical downlink transmission rate, historical latency, and historical reliability of the first carrier. The sample set is divided into a training set and a test set according to a preset ratio. Historical terminal status parameters and historical network performance parameters of the first carrier are used as input, and historical transmission performance parameters of the first carrier when transmitting service data of the target service type are used as output. The GSDT model is trained using the training set. The trained GSDT model is then fine-tuned using the test set to obtain a pre-trained first GSDT model.

[0062] For example, after obtaining the pre-trained first GSDT model, the terminal state parameters and the network performance parameters of the first carrier are used as inputs to the pre-trained first GSDT model to obtain the first prediction result.

[0063] Thus, the method to obtain the first prediction result can be clearly defined. Obtaining the first prediction result through the pre-trained first GSDT model can improve the accuracy of the prediction result and improve the efficiency of data processing.

[0064] S103. Based on the terminal status parameters and the network performance parameters of the second carrier, determine the second prediction result.

[0065] For example, the network performance parameters of the second carrier include the number of RRC connected users of the second carrier, the PRB utilization of the second carrier, the downlink PRB utilization of the second carrier, and the QCI of the second carrier.

[0066] The second prediction result is used to indicate the transmission performance that can be achieved when transmitting service data of the target service type on the second carrier.

[0067] For example, the second prediction results include uplink transmission rate, downlink transmission rate, latency, and reliability.

[0068] In some embodiments, the terminal state parameters and the network performance parameters of the second carrier are processed by a pre-trained second gradient boosting decision tree (GSDT) model to obtain a second prediction result.

[0069] For example, parameter information from the historical usage of the target service type on the second carrier is used as a sample set. For instance, historical terminal status parameters, historical network performance parameters of the second carrier, and historical transmission performance parameters of the second carrier when transmitting service data of the target service type are used as the sample set. Historical terminal status parameters include the terminal's historical RSRP, historical SINR, and historical mobility speed. Historical network performance parameters of the second carrier include the historical RRC connected users, historical PRB utilization, downlink PRB utilization, and historical QCI. Historical transmission performance parameters of the second carrier when transmitting service data of the target service type include the historical uplink transmission rate, historical downlink transmission rate, historical latency, and historical reliability of the second carrier. The sample set is divided into a training set and a test set according to a preset ratio. Historical terminal status parameters and historical network performance parameters of the second carrier are used as input, and historical transmission performance parameters of the second carrier when transmitting service data of the target service type are used as output. The GSDT model is trained using the training set. The trained GSDT model is then fine-tuned using the test set to obtain a pre-trained second GSDT model.

[0070] For example, after obtaining the pre-trained second GSDT model, the terminal state parameters and the network performance parameters of the second carrier are used as inputs to the pre-trained second GSDT model to obtain the second prediction result.

[0071] Thus, the method to obtain the second prediction result can be clearly defined. By obtaining the second prediction result through the pre-trained second GSDT model, the accuracy of the prediction result can be improved, and the efficiency of data processing can be improved.

[0072] It should be noted that the frequencies of the first carrier and the second carrier are different. For example, the frequency of the first carrier is greater than the frequency of the second carrier; or, the frequency of the second carrier is greater than the frequency of the first carrier.

[0073] S104. Based on the first prediction result and the second prediction result, determine the target carrier from the first carrier and the second carrier.

[0074] The target carrier is the carrier that transmits service data of the target service type.

[0075] For example, based on the first prediction result and the second prediction result, the first carrier is determined as the target carrier from the first carrier and the second carrier.

[0076] For example, based on the first prediction result and the second prediction result, the second carrier is determined as the target carrier from the first carrier and the second carrier.

[0077] For example, based on the first prediction result and the second prediction result, the first carrier and the second carrier are determined as the target carrier from the first carrier and the second carrier.

[0078] The carrier determination method provided in this application obtains a first prediction result, i.e., the transmission performance that the first carrier can achieve when transmitting service data of the target service type, using terminal status parameters and network performance parameters of the first carrier. Furthermore, it obtains a second prediction result, i.e., the transmission performance that the second carrier can achieve when transmitting service data of the target service type, using terminal status parameters and network performance parameters of the second carrier. By fully utilizing parameter information from both the terminal and network sides, the prediction results for carriers of different frequencies are determined, making the prediction results more consistent with the actual usage of the current carrier. Carrier selection based on the prediction results of different carriers ensures that the selected target carrier better meets the service requirements of the target service type, resulting in more rational carrier resource allocation, ensuring that network service quality meets service needs, and avoiding resource waste.

[0079] The following is about the above. Figure 1 The process of determining the target service type in step S101 will be described. In one possible implementation, the process of determining the target service type in step S101 includes the following two methods.

[0080] Method 1: When the business data is transmitted in plaintext, the above process of determining the target business type can be as follows: In response to the plaintext transmission of business data, the target business type corresponding to the terminal's business data is determined by deep packet inspection (DPI) technology.

[0081] For example, business data includes information such as Uniform Resource Locator (URL) and protocol fields. The target business type is obtained by analyzing the business data using DPI.

[0082] In this way, when business data is transmitted in plaintext, the target service type can be directly identified through DPI, which facilitates the subsequent determination of the target carrier based on the target service type.

[0083] Method 2: When the business data is transmitted in encrypted form, the above process of determining the target business type can be achieved through the following steps 11 to 12.

[0084] Step 11: In the case of encrypted transmission of business data, detect the similarity between the traffic feature parameters and the standard traffic feature parameters in the knowledge base based on the traffic feature parameters of the business data.

[0085] The knowledge base is used to store at least one standard service template. The standard service template includes a standard service type, as well as the standard service category, standard service sub-category, standard traffic characteristic parameters, and standard transmission performance parameters corresponding to the standard service type.

[0086] When business data is transmitted in encrypted form, it means that the target business type corresponding to the business data cannot be determined from the content of the business data transmission.

[0087] For example, the traffic characteristic parameters of business data include uplink / downlink ratio, packet sending frequency, and packet size.

[0088] For example, standard traffic characteristic parameters include standard uplink / downlink ratio, standard packet transmission frequency, and standard packet size.

[0089] For example, standard transmission performance parameters include standard uplink transmission rate, standard downlink transmission rate, standard latency, and standard reliability.

[0090] For example, traffic characteristic parameters of the business data can be obtained by analyzing the tcpdump or wireshark tools. For instance, the uplink / downlink ratio, packet frequency, and packet size can be obtained through analysis of the business data.

[0091] For example, pattern matching is used to detect the similarity between traffic feature parameters and standard traffic feature parameters in the knowledge base. For instance, pattern matching can be used to detect the similarity between the uplink / downlink ratio and the standard uplink / downlink ratio; the similarity between the packet sending frequency and the standard packet sending frequency; and the similarity between the packet size and the standard packet size.

[0092] For example, Table 1 is a standard business template example table in a knowledge base provided in an embodiment of this application.

[0093] Table 1

[0094] Furthermore, the knowledge base may include other parameters, which are not limited in this application. The standard business types in the knowledge base can be traditional businesses or emerging businesses.

[0095] Step 12: If there are standard traffic feature parameters in the knowledge base that meet the similarity threshold, determine the standard business type corresponding to the standard traffic feature parameter as the target business type.

[0096] For example, the threshold condition could be a similarity threshold. The similarity threshold is used to determine whether a standard traffic feature parameter similar to the traffic feature parameter exists in the knowledge base.

[0097] If there are standard traffic feature parameters in the knowledge base that meet the similarity threshold, it means that there are standard traffic feature parameters in the knowledge base that are similar to the traffic feature parameters of the current business data. In other words, there are standard business types in the knowledge base that are similar to the business types currently in use, and the target business type can be determined from the knowledge base.

[0098] When multiple similarity scores all meet the threshold condition, the standard service type corresponding to the standard traffic feature parameter with the highest similarity is determined as the target service type. This makes the determined target service type more consistent with actual usage and more accurate.

[0099] Thus, when business data is transmitted in encrypted form, by comparing the traffic characteristic parameters of the business data with the standard traffic characteristic parameters in the knowledge base, the standard business type corresponding to the standard traffic characteristic parameters similar to the current situation can be used as the target business type, which can reduce the time spent determining the target business type and improve efficiency.

[0100] The following is about the above. Figure 1 The process of determining the target carrier in step S104 will be explained. In one possible implementation, the process of determining the target carrier in step S104 can be implemented by the following step 21.

[0101] Step 21: Based on the first prediction result, the second prediction result, and the standard transmission performance parameters corresponding to the target service type, determine the target carrier from the first carrier and the second carrier.

[0102] For example, the first prediction result includes the uplink transmission rate of the first carrier, the downlink transmission rate of the first carrier, the delay of the first carrier, and the reliability of the first carrier.

[0103] For example, the second prediction result includes the uplink transmission rate of the second carrier, the downlink transmission rate of the second carrier, the delay of the second carrier, and the reliability of the second carrier.

[0104] For example, standard transmission performance parameters include standard uplink transmission rate, standard downlink transmission rate, standard latency, and standard reliability.

[0105] For example, a target carrier is determined from a first carrier and a second carrier by the degree of deviation between the first prediction result and the standard transmission performance parameters, and the degree of deviation between the second prediction result and the standard transmission performance parameters.

[0106] Thus, the target carrier can be determined using the first prediction result, the second prediction result, and standard transmission performance parameters. By combining factors such as network load, scheduling strategy, terminal mobility speed, and target service type, a specific carrier is dynamically selected for service data transmission, ensuring the performance of service data transmission.

[0107] In one possible implementation, either the first prediction result or the second prediction result includes uplink transmission rate, downlink transmission rate, latency, and reliability; the standard transmission performance parameters include standard uplink transmission rate, standard downlink transmission rate, standard latency, and standard reliability. In this case, the process of determining the target carrier in step 21 above can be implemented through steps 31 to 33.

[0108] Step 31: In response to the fact that both the first prediction result and the second prediction result meet the service requirement, the target carrier is determined from the first carrier and the second carrier based on the satisfaction score of the first carrier and the satisfaction score of the second carrier.

[0109] The satisfaction score of the first carrier is used to indicate the degree of conformity between the first prediction result and the standard transmission performance parameters, and the satisfaction score of the second carrier is used to indicate the degree of conformity between the second prediction result and the standard transmission performance parameters.

[0110] The business requirements include that the uplink transmission rate of the predicted result is greater than or equal to the standard uplink transmission rate, the downlink transmission rate of the predicted result is greater than or equal to the standard downlink transmission rate, the latency of the predicted result is less than or equal to the standard latency, and the reliability of the predicted result is greater than or equal to the standard reliability.

[0111] If the first prediction result meets the service requirement, then the uplink transmission rate of the first prediction result in the first carrier is greater than or equal to the standard uplink transmission rate, the downlink transmission rate of the first prediction result is greater than or equal to the standard downlink transmission rate, the delay of the first prediction result is less than or equal to the standard delay, and the reliability of the first prediction result is greater than or equal to the standard reliability.

[0112] If the second prediction result meets the service requirement conditions, then the uplink transmission rate of the second prediction result in the second carrier is greater than or equal to the standard uplink transmission rate, the downlink transmission rate of the second prediction result is greater than or equal to the standard downlink transmission rate, the delay of the second prediction result is less than or equal to the standard delay, and the reliability of the second prediction result is greater than or equal to the standard reliability.

[0113] Understandably, if the prediction results meet the service requirements, it means that the current performance of the carrier can meet the network requirements for the transmission of the target service type.

[0114] When both the first and second prediction results meet the service requirements, it indicates that both the first and second carriers can meet the performance requirements for data transmission of the target service type. In other words, selecting either the first or second carrier will satisfy user needs, ensuring a good user experience. In this case, determining the target carrier based on the satisfaction scores of the first and second carriers ensures that the chosen target carrier better meets the service requirements.

[0115] Step 32: In response to the first prediction result or the second prediction result satisfying the service requirement conditions, determine the carrier that satisfies the service requirement conditions among the first carrier and the second carrier as the target carrier.

[0116] When the first prediction result meets the service requirement conditions, it means that the first carrier can meet the performance requirements required for data transmission of the target service type, and the first carrier is determined as the target carrier.

[0117] When the second prediction result meets the service requirement conditions, it means that the second carrier can meet the performance requirements required for data transmission of the target service type, and the second carrier is determined as the target carrier.

[0118] Using carriers that meet the business requirements as target carriers can ensure the smoothness and stability of services, enabling network performance to be precisely matched with business needs, optimizing resources, and improving user experience.

[0119] Step 33: In response to the fact that neither the first prediction result nor the second prediction result meets the service requirement conditions, the first carrier and the second carrier are determined as the target carriers.

[0120] When neither the first prediction result nor the second prediction result meets the service requirement conditions, it means that the current network performance of the first carrier and the second carrier cannot meet the service transmission requirements of the target service type. In this case, using the first carrier and the second carrier as target carriers to transmit service data simultaneously can improve throughput and service transmission effect.

[0121] In this way, the process of determining the target carrier under different conditions based on the first and second prediction results can be clearly defined.

[0122] In some practical applications, the process of determining the target carrier in step 31 above includes steps one and two.

[0123] Step 1: In response to the satisfaction score of the first carrier being greater than or equal to the satisfaction score of the second carrier, the first carrier is determined as the target carrier.

[0124] The satisfaction score indicates the degree of conformity between the predicted result and the standard transmission performance parameters; that is, the higher the satisfaction score, the better the conformity between the predicted result and the standard transmission performance parameters. When the satisfaction score of the first carrier is greater than or equal to the satisfaction score of the second carrier, it means that the degree of conformity between the first carrier and the standard transmission performance parameters is greater than or equal to the degree of conformity between the second carrier and the standard transmission performance parameters. In other words, the current performance state of the first carrier better meets the current service transmission requirements, and selecting the first carrier as the target carrier is more in line with user needs.

[0125] Step 2: In response to the fact that the satisfaction score of the first carrier is less than the satisfaction score of the second carrier, the second carrier is determined as the target carrier.

[0126] When the satisfaction score of the first carrier is less than that of the second carrier, it means that the degree of conformity between the first carrier and the standard transmission performance parameters is less than that between the second carrier and the standard transmission performance parameters. In other words, the current performance state of the second carrier better meets the current service transmission requirements, and selecting the second carrier as the target carrier is more in line with the user's needs.

[0127] In some practical applications, the process of determining the satisfaction score of the first carrier includes the following steps 41 to 45.

[0128] Step 41: Determine the first score of the first carrier based on the uplink transmission rate of the first prediction result and the standard uplink transmission rate of the standard transmission performance parameters.

[0129] The first score of the first carrier is used to characterize the degree of conformity between the uplink transmission rate of the first carrier and the standard uplink transmission rate of the standard transmission performance parameters.

[0130] For example, the difference between the uplink transmission rate of the first prediction result and the standard uplink transmission rate of the standard transmission performance parameters is determined as the first difference of the first carrier, and the ratio between the first difference of the first carrier and the standard uplink transmission rate of the standard transmission performance parameters is determined as the first score of the first carrier. That is, the first score of the first carrier is determined in the following manner.

[0131] The first score of the first carrier = (uplink transmission rate of the first prediction result - standard uplink transmission rate of the standard transmission performance parameter) / standard uplink transmission rate of the standard transmission performance parameter.

[0132] When the uplink transmission rate of the first prediction result meets the service requirements, i.e., the uplink transmission rate of the first prediction result is greater than or equal to the standard uplink transmission rate of the standard transmission performance parameters, the first score of the first carrier is greater than or equal to 0. When the uplink transmission rate of the first prediction result does not meet the service requirements, i.e., the uplink transmission rate of the first prediction result is less than the standard uplink transmission rate of the standard transmission performance parameters, the first score of the first carrier is negative.

[0133] Step 42: Based on the downlink transmission rate of the first prediction result and the standard downlink transmission rate of the standard transmission performance parameters, determine the second score of the first carrier.

[0134] The second score of the first carrier is used to characterize the degree of conformity between the downlink transmission rate of the first carrier and the standard downlink transmission rate of the standard transmission performance parameters.

[0135] For example, the difference between the downlink transmission rate of the first prediction result and the standard downlink transmission rate of the standard transmission performance parameters is determined as the second difference of the first carrier, and the ratio between the second difference of the first carrier and the standard downlink transmission rate of the standard transmission performance parameters is determined as the second score of the first carrier. That is, the second score of the first carrier is determined in the following manner.

[0136] The second score of the first carrier = (downlink transmission rate of the first prediction result - standard downlink transmission rate of the standard transmission performance parameter) / standard downlink transmission rate of the standard transmission performance parameter.

[0137] When the downlink transmission rate of the first prediction result meets the service requirements, i.e., the downlink transmission rate of the first prediction result is greater than or equal to the standard downlink transmission rate of the standard transmission performance parameters, the second score of the first carrier is greater than or equal to 0. When the downlink transmission rate of the first prediction result does not meet the service requirements, i.e., the downlink transmission rate of the first prediction result is less than the standard downlink transmission rate of the standard transmission performance parameters, the second score of the first carrier is negative.

[0138] Step 43: Determine the third score of the first carrier based on the standard delay of the standard transmission performance parameters and the delay of the first prediction result.

[0139] The third score of the first carrier is used to characterize the degree of conformity between the delay of the first carrier and the standard delay of the standard transmission performance parameters.

[0140] For example, the difference between the standard delay of the standard transmission performance parameters and the delay of the first prediction result is determined as the third difference of the first carrier, and the ratio between the third difference of the first carrier and the delay of the first prediction result is determined as the third score of the first carrier. That is, the third score of the first carrier is determined in the following manner.

[0141] The third score of the first carrier = (standard delay of standard transmission performance parameters - delay of the first prediction result) / delay of the first prediction result.

[0142] When the delay of the first prediction result meets the service requirements, i.e., the standard delay of the standard transmission performance parameter is greater than or equal to the delay of the first prediction result, the third score of the first carrier is greater than or equal to 0. When the delay of the first prediction result does not meet the service requirements, i.e., the standard delay of the standard transmission performance parameter is less than the delay of the first prediction result, the third score of the first carrier is negative.

[0143] Step 44: Determine the fourth score of the first carrier based on the reliability of the first prediction result and the standard reliability of the standard transmission performance parameters.

[0144] The fourth score of the first carrier is used to characterize the degree of conformity between the reliability of the first carrier and the standard reliability of the standard transmission performance parameters.

[0145] For example, the difference between the reliability of the first prediction result and the standard reliability of the standard transmission performance parameters is determined as the fourth difference of the first carrier, and the ratio between the fourth difference of the first carrier and the standard reliability of the standard transmission performance parameters is determined as the fourth score of the first carrier. That is, the fourth score of the first carrier is determined in the following manner.

[0146] The fourth score of the first carrier = (Reliability of the first prediction result - Standard reliability of the standard transmission performance parameters) / Standard reliability of the standard transmission performance parameters.

[0147] When the reliability of the first prediction result meets the service requirements, i.e., the reliability of the first prediction result is greater than or equal to the standard reliability of the standard transmission performance parameters, the fourth score of the first carrier is greater than or equal to 0. When the reliability of the first prediction result does not meet the service requirements, i.e., the reliability of the first prediction result is less than the standard reliability of the standard transmission performance parameters, the fourth score of the first carrier is negative.

[0148] Step 45: Determine the satisfaction score of the first carrier based on the first score, the second score, the third score, and the fourth score of the first carrier.

[0149] For example, the sum of the first score, the second score, the third score, and the fourth score of the first carrier is determined as the satisfaction score of the first carrier.

[0150] For example, the first carrier's first score, second score, third score, and fourth score are weighted and summed to obtain the first carrier's satisfaction score.

[0151] In this way, the satisfaction score of the first carrier can be calculated from four aspects: uplink transmission rate, downlink transmission rate, latency, and reliability, so that the satisfaction score of the determined first carrier can more comprehensively reflect the degree of conformity between the first carrier and the standard transmission performance parameters.

[0152] In some practical applications, the process of determining the satisfaction score of the second carrier includes the following steps 51 to 55.

[0153] Step 51: Based on the uplink transmission rate of the second prediction result and the standard uplink transmission rate of the standard transmission performance parameters, determine the first score of the second carrier.

[0154] The first score of the second carrier is used to characterize the degree of conformity between the uplink transmission rate of the second carrier and the standard uplink transmission rate of the standard transmission performance parameters.

[0155] For example, the difference between the uplink transmission rate of the second prediction result and the standard uplink transmission rate of the standard transmission performance parameters is determined as the first difference of the second carrier, and the ratio between the first difference of the second carrier and the standard uplink transmission rate of the standard transmission performance parameters is determined as the first score of the second carrier. That is, the first score of the second carrier is determined in the following manner.

[0156] The first score of the second carrier = (uplink transmission rate of the second prediction result - standard uplink transmission rate of the standard transmission performance parameter) / standard uplink transmission rate of the standard transmission performance parameter.

[0157] When the uplink transmission rate of the second prediction result meets the service requirements, i.e., the uplink transmission rate of the second prediction result is greater than or equal to the standard uplink transmission rate of the standard transmission performance parameters, the first score of the second carrier is greater than or equal to 0. When the uplink transmission rate of the second prediction result does not meet the service requirements, i.e., the uplink transmission rate of the second prediction result is less than the standard uplink transmission rate of the standard transmission performance parameters, the first score of the second carrier is negative.

[0158] Step 52: Based on the downlink transmission rate of the second prediction result and the standard downlink transmission rate of the standard transmission performance parameters, determine the second score of the second carrier.

[0159] The second score of the second carrier is used to characterize the degree of conformity between the downlink transmission rate of the second carrier and the standard downlink transmission rate of the standard transmission performance parameters.

[0160] For example, the difference between the downlink transmission rate of the second prediction result and the standard downlink transmission rate of the standard transmission performance parameters is determined as the second difference of the second carrier, and the ratio between the second difference of the second carrier and the standard downlink transmission rate of the standard transmission performance parameters is determined as the second score of the second carrier. That is, the second score of the second carrier is determined in the following manner.

[0161] The second score of the second carrier = (downlink transmission rate of the second prediction result - standard downlink transmission rate of the standard transmission performance parameter) / standard downlink transmission rate of the standard transmission performance parameter.

[0162] When the downlink transmission rate of the second prediction result meets the service requirements, i.e., the downlink transmission rate of the second prediction result is greater than or equal to the standard downlink transmission rate of the standard transmission performance parameters, the second score of the second carrier is greater than or equal to 0. When the downlink transmission rate of the second prediction result does not meet the service requirements, i.e., the downlink transmission rate of the second prediction result is less than the standard downlink transmission rate of the standard transmission performance parameters, the second score of the second carrier is negative.

[0163] Step 53: Determine the third score of the second carrier based on the standard delay of the standard transmission performance parameters and the delay of the second prediction result.

[0164] The third score of the second carrier is used to characterize the degree of conformity between the delay of the second carrier and the standard delay of the standard transmission performance parameters.

[0165] For example, the difference between the standard delay of the standard transmission performance parameters and the delay of the second prediction result is determined as the third difference of the second carrier, and the ratio between the third difference of the second carrier and the delay of the second prediction result is determined as the third score of the second carrier. That is, the third score of the second carrier is determined in the following manner.

[0166] The third score of the second carrier = (standard delay of standard transmission performance parameters - delay of the second prediction result) / delay of the second prediction result.

[0167] When the delay of the second prediction result meets the service requirements, i.e., the standard delay of the standard transmission performance parameter is greater than or equal to the delay of the second prediction result, the third score of the second carrier is greater than or equal to 0. When the delay of the second prediction result does not meet the service requirements, i.e., the standard delay of the standard transmission performance parameter is less than the delay of the second prediction result, the third score of the second carrier is negative.

[0168] Step 54: Based on the reliability of the second prediction result and the standard reliability of the standard transmission performance parameters, determine the fourth score of the second carrier.

[0169] The fourth score of the second carrier is used to characterize the degree of conformity between the reliability of the second carrier and the standard reliability of the standard transmission performance parameters.

[0170] For example, the difference between the reliability of the second prediction result and the standard reliability of the standard transmission performance parameters is determined as the fourth difference of the second carrier, and the ratio between the fourth difference of the second carrier and the standard reliability of the standard transmission performance parameters is determined as the fourth score of the second carrier. That is, the fourth score of the second carrier is determined in the following manner.

[0171] The fourth score of the second carrier = (Reliability of the second prediction result - Standard reliability of the standard transmission performance parameter) / Standard reliability of the standard transmission performance parameter.

[0172] When the reliability of the second prediction result meets the service requirements, i.e., the reliability of the second prediction result is greater than or equal to the standard reliability of the standard transmission performance parameters, the fourth score of the second carrier is greater than or equal to 0. When the reliability of the second prediction result does not meet the service requirements, i.e., the reliability of the second prediction result is less than the standard reliability of the standard transmission performance parameters, the fourth score of the second carrier is negative.

[0173] Step 55: Determine the satisfaction score of the second carrier based on the first score, the second score, the third score, and the fourth score of the second carrier.

[0174] For example, the sum of the first score, the second score, the third score, and the fourth score of the second carrier is determined as the satisfaction score of the first carrier.

[0175] For example, the first score, the second score, the third score, and the fourth score of the second carrier are weighted and summed to obtain the satisfaction score of the first carrier.

[0176] In this way, the satisfaction score of the second carrier can be calculated from four aspects: uplink transmission rate, downlink transmission rate, latency, and reliability. This allows the determined satisfaction score of the second carrier to more comprehensively reflect the degree of conformity between the second carrier and the standard transmission performance parameters.

[0177] For example, Table 2 is a carrier satisfaction rating table provided in an embodiment of this application.

[0178] Table 2

[0179] Furthermore, after determining the target carrier, real-time feedback data for that target carrier can be obtained. This real-time feedback data includes the target carrier's uplink transmission rate, downlink transmission rate, latency, and reliability. Based on the deviation between the real-time feedback data and the prediction results for the target carrier, the model used to determine the prediction results is adjusted.

[0180] For example, the deviation of the uplink transmission rate = |uplink transmission rate of the target carrier - uplink transmission rate of the predicted result| / uplink transmission rate of the predicted result.

[0181] For example, the deviation of the downlink transmission rate = |downlink transmission rate of the target carrier - predicted downlink transmission rate| / predicted downlink transmission rate.

[0182] For example, the delay deviation = |target carrier delay - prediction result delay| / prediction result delay.

[0183] For example, the reliability deviation = |reliability of the target carrier - reliability of the prediction result| / reliability of the prediction result.

[0184] For example, when the target carrier is the first carrier, the pre-trained first GSDT model is adjusted based on the deviation between the real-time feedback data of the first carrier and the first prediction result of the first carrier.

[0185] For example, when the target carrier is the second carrier, the pre-trained second GSDT model is adjusted based on the deviation between the real-time feedback data of the second carrier and the second prediction result of the second carrier.

[0186] For example, when the target carrier is a first carrier and a second carrier, the pre-trained first GSDT model is adjusted according to the deviation between the real-time feedback data of the first carrier and the first prediction result of the first carrier; the pre-trained second GSDT model is adjusted according to the deviation between the real-time feedback data of the second carrier and the second prediction result of the second carrier.

[0187] By acquiring real-time feedback data, the model can be adjusted, thereby adjusting the prediction results so that the determined target carrier can better meet user needs and satisfy various user service experiences.

[0188] As an example, the carrier determination method shown in the above method embodiment can divide the carrier determination system into modules. Figure 2 This is a schematic diagram illustrating the module division of a carrier determination system provided in an embodiment of this application. Figure 2 As shown, the carrier determination system includes a service requirement knowledge base module, a service identification module, a carrier selection module, and an evaluation module.

[0189] The business requirements knowledge base module includes a knowledge base.

[0190] The service identification module is used to determine the target service type corresponding to the service data of the terminal.

[0191] The carrier selection module is used to determine a first prediction result based on terminal state parameters and network performance parameters of a first carrier, and to determine a second prediction result based on terminal state parameters and network performance parameters of a second carrier. Furthermore, the carrier selection module is used to determine a target carrier from the first carrier and the second carrier based on the first and second prediction results.

[0192] The evaluation module is used to obtain real-time feedback data and adjust the model.

[0193] This application embodiment can divide the carrier determination device into functional modules or functional units according to the above method example. For example, each function can be divided into a separate functional module or functional unit, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or in software functional modules or functional units. The module or unit division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0194] Figure 3 This is a schematic diagram of a carrier determination device 30 provided in an embodiment of this application. The carrier determination device 30 includes: a first determination unit 301, used to determine the target service type corresponding to the service data of a terminal; a second determination unit 302, used to determine a first prediction result based on terminal state parameters and network performance parameters of a first carrier, wherein the terminal state parameters indicate the channel state and mobility state of the terminal, and the first prediction result indicates the transmission performance that can be achieved when the target service type service data is transmitted on the first carrier; a third determination unit 303, used to determine a second prediction result based on the terminal state parameters and network performance parameters of a second carrier, wherein the second prediction result indicates the transmission performance that can be achieved when the target service type service data is transmitted on the second carrier; and a fourth determination unit 304, used to determine a target carrier from the first carrier and the second carrier based on the first prediction result and the second prediction result; wherein the frequency of the first carrier is different from the frequency of the second carrier.

[0195] In one possible implementation, the first determining unit 301 is used to: in the case of encrypted transmission of business data, detect the similarity between the traffic feature parameters and standard traffic feature parameters in the knowledge base based on the traffic feature parameters of the business data; wherein, the knowledge base is used to store at least one standard business template, the standard business template including a standard business type, and a standard business category, a standard business subclass, a standard traffic feature parameter, and a standard transmission performance parameter corresponding to the standard business type; if there are standard traffic feature parameters in the knowledge base whose similarity meets the threshold condition, determine the standard business type corresponding to the standard traffic feature parameter as the target business type.

[0196] In one possible implementation, the first determining unit 301 is used to: in response to the plaintext transmission of service data, determine the target service type corresponding to the service data of the terminal by using deep packet inspection (DPI) technology.

[0197] In one possible implementation, the fourth determining unit 304 is used to: determine the target carrier from the first carrier and the second carrier based on the first prediction result, the second prediction result and the standard transmission performance parameters corresponding to the target service type.

[0198] In one possible implementation, either the first prediction result or the second prediction result includes uplink transmission rate, downlink transmission rate, latency, and reliability; the standard transmission performance parameters include standard uplink transmission rate, standard downlink transmission rate, standard latency, and standard reliability; the fourth determining unit 304 is configured to: in response to the condition that both the first prediction result and the second prediction result meet the service requirements, determine a target carrier from the first carrier and the second carrier based on the satisfaction score of the first carrier and the satisfaction score of the second carrier, wherein the satisfaction score of the first carrier is used to indicate the degree of conformity between the first prediction result and the standard transmission performance parameters, and the satisfaction score of the second carrier... Used to indicate the degree of conformity between the second prediction result and the standard transmission performance parameters; in response to the first prediction result or the second prediction result meeting the service requirement conditions, the carrier among the first carrier and the second carrier that meets the service requirement conditions is determined as the target carrier; in response to the first prediction result and the second prediction result not meeting the service requirement conditions, the first carrier and the second carrier are determined as the target carrier; the service requirement conditions include that the uplink transmission rate of the prediction result is greater than or equal to the standard uplink transmission rate, and the downlink transmission rate of the prediction result is greater than or equal to the standard downlink transmission rate, and the delay of the prediction result is less than or equal to the standard delay, and the reliability of the prediction result is greater than or equal to the standard reliability.

[0199] In one possible implementation, the fourth determining unit 304 is configured to: determine the first carrier as the target carrier in response to the satisfaction score of the first carrier being greater than or equal to the satisfaction score of the second carrier; and determine the second carrier as the target carrier in response to the satisfaction score of the first carrier being less than the satisfaction score of the second carrier.

[0200] In one possible implementation, the fourth determining unit 304 is configured to: determine a first score for a first carrier based on the uplink transmission rate of the first prediction result and the standard uplink transmission rate of the standard transmission performance parameters, wherein the first score of the first carrier characterizes the degree of conformity between the uplink transmission rate of the first carrier and the standard uplink transmission rate of the standard transmission performance parameters; determine a second score for the first carrier based on the downlink transmission rate of the first prediction result and the standard downlink transmission rate of the standard transmission performance parameters, wherein the second score of the first carrier characterizes the degree of conformity between the downlink transmission rate of the first carrier and the standard downlink transmission rate of the standard transmission performance parameters; determine a third score for the first carrier based on the standard delay of the standard transmission performance parameters and the delay of the first prediction result, wherein the third score of the first carrier characterizes the degree of conformity between the delay of the first carrier and the standard delay of the standard transmission performance parameters; determine a fourth score for the first carrier based on the reliability of the first prediction result and the standard reliability of the standard transmission performance parameters, wherein the fourth score of the first carrier characterizes the degree of conformity between the reliability of the first carrier and the standard reliability of the standard transmission performance parameters; and determine a satisfaction score for the first carrier based on the first score, the second score, the third score, and the fourth score of the first carrier.

[0201] In one possible implementation, the fourth determining unit 304 is configured to: determine a first score for the second carrier based on the uplink transmission rate of the second prediction result and the standard uplink transmission rate of the standard transmission performance parameters, wherein the first score of the second carrier characterizes the degree of conformity between the uplink transmission rate of the second carrier and the standard uplink transmission rate of the standard transmission performance parameters; determine a second score for the second carrier based on the downlink transmission rate of the second prediction result and the standard downlink transmission rate of the standard transmission performance parameters, wherein the second score of the second carrier characterizes the degree of conformity between the downlink transmission rate of the second carrier and the standard downlink transmission rate of the standard transmission performance parameters; determine a third score for the second carrier based on the standard delay of the standard transmission performance parameters and the delay of the second prediction result, wherein the third score of the second carrier characterizes the degree of conformity between the delay of the second carrier and the standard delay of the standard transmission performance parameters; determine a fourth score for the second carrier based on the reliability of the second prediction result and the standard reliability of the standard transmission performance parameters, wherein the fourth score of the second carrier characterizes the degree of conformity between the reliability of the second carrier and the standard reliability of the standard transmission performance parameters; and determine a satisfaction score for the second carrier based on the first score, the second score, the third score, and the fourth score of the second carrier.

[0202] In one possible implementation, the second determining unit 302 is used to: process the terminal state parameters and the network performance parameters of the first carrier through a pre-trained first gradient boosting decision tree (GSDT) model to obtain a first prediction result; the third determining unit 303 is used to: process the terminal state parameters and the network performance parameters of the second carrier through a pre-trained second gradient boosting decision tree (GSDT) model to obtain a second prediction result.

[0203] Through the above description of the embodiments, those skilled in the art will clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0204] When implemented in hardware, the various modules in the carrier determination device can be integrated into, for example... Figure 4 The carrier determination device shown is implemented in hardware. Specifically, as... Figure 4 As shown, the basic hardware structure of the carrier determination device is introduced.

[0205] Figure 4 This is a schematic diagram of the hardware structure of a carrier determination device provided in an embodiment of this application. Figure 4 As shown, the carrier determination device includes at least one processor 401, a communication line 402, and at least one communication interface 404, and may also include a memory 403. The processor 401, memory 403, and communication interface 404 are connected via the communication line 402.

[0206] The processor 401 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0207] Communication line 402 may include a path for transmitting information between the aforementioned components.

[0208] Communication interface 404 is used to communicate with other devices or communication networks. It can use any transceiver-like device, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0209] The memory 403 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of including or storing desired program code having the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0210] In one possible design, the memory 403 can exist independently of the processor 401, meaning the memory 403 can be an external memory of the processor 401. In this case, the memory 403 can be connected to the processor 401 via a communication line 402 to store execution instructions or application code, and its execution is controlled by the processor 401 to implement the carrier determination method provided in the following embodiments of this application. In another possible design, the memory 403 can also be integrated with the processor 401, meaning the memory 403 can be an internal memory of the processor 401. For example, the memory 403 can be a cache, used to temporarily store some data and instruction information.

[0211] As one possible implementation, processor 401 may include one or more CPUs, for example Figure 4 CPU0 and CPU1 in the example. As another possible implementation, the carrier determination device may include multiple processors, such as... Figure 4 The processors 401 and 407 are included. As another possible implementation, the carrier determination device may also include an output device 405 and an input device 406.

[0212] This application provides a computer program product containing instructions that, when run on a computer, cause the computer to execute the carrier determination method in the above method embodiments.

[0213] This application also provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the carrier determination method in the method flow shown in the above method embodiments.

[0214] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), a register, a hard disk, an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof, or any other form of computer-readable storage medium known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may reside in an application-specific integrated circuit (ASIC). In the embodiments of this application, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0215] Since the carrier determination device, computer-readable storage medium, and computer program product in the embodiments of this application can be applied to the above method, the technical effects that can be obtained can also be referred to the above method embodiments. The embodiments of this application will not be repeated here.

[0216] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0217] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0218] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0219] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A carrier wave determination method, characterized in that, The method includes: Determine the target service type corresponding to the terminal's service data; Based on terminal status parameters and network performance parameters of the first carrier, a first prediction result is determined. The terminal status parameters are used to indicate the channel state and mobility state of the terminal, and the first prediction result is used to indicate the transmission performance that can be achieved when transmitting service data of the target service type on the first carrier. Based on the terminal status parameters and the network performance parameters of the second carrier, a second prediction result is determined. The second prediction result is used to indicate the transmission performance that can be achieved when transmitting service data of the target service type on the second carrier. Based on the first prediction result and the second prediction result, the target carrier is determined from the first carrier and the second carrier; The frequency of the first carrier is different from the frequency of the second carrier.

2. The method according to claim 1, characterized in that, The determination of the target service type corresponding to the service data of the terminal includes: In the case of encrypted transmission of the business data, the similarity between the traffic feature parameters of the business data and the standard traffic feature parameters in the knowledge base is detected based on the traffic feature parameters of the business data; wherein, the knowledge base is used to store at least one standard business template, the standard business template includes a standard business type, and a standard business category, a standard business subclass, a standard traffic feature parameter and a standard transmission performance parameter corresponding to the standard business type; If there are standard traffic feature parameters in the knowledge base that meet the similarity threshold, the standard service type corresponding to the standard traffic feature parameter is determined as the target service type.

3. The method according to claim 1, characterized in that, The determination of the target service type corresponding to the service data of the terminal includes: In response to the plaintext transmission of the service data, the target service type corresponding to the service data of the terminal is determined by Deep Packet Inspection (DPI) technology.

4. The method according to claim 1, characterized in that, The step of determining the target carrier from the first carrier and the second carrier based on the first prediction result and the second prediction result includes: Based on the first prediction result, the second prediction result, and the standard transmission performance parameters corresponding to the target service type, the target carrier is determined from the first carrier and the second carrier.

5. The method according to claim 4, characterized in that, The first prediction result and the second prediction result include uplink transmission rate, downlink transmission rate, latency, and reliability; the standard transmission performance parameters include standard uplink transmission rate, standard downlink transmission rate, standard latency, and standard reliability. The step of determining the target carrier from the first carrier and the second carrier based on the first prediction result, the second prediction result, and the standard transmission performance parameters corresponding to the target service type includes: In response to the fact that both the first prediction result and the second prediction result meet the service requirement conditions, the target carrier is determined from the first carrier and the second carrier based on the satisfaction score of the first carrier and the satisfaction score of the second carrier. The satisfaction score of the first carrier is used to indicate the degree of conformity between the first prediction result and the standard transmission performance parameters, and the satisfaction score of the second carrier is used to indicate the degree of conformity between the second prediction result and the standard transmission performance parameters. In response to the first prediction result or the second prediction result satisfying the service requirement condition, the carrier that satisfies the service requirement condition among the first carrier and the second carrier is determined as the target carrier; In response to the fact that neither the first prediction result nor the second prediction result meets the service requirement condition, the first carrier and the second carrier are determined as the target carrier; The service requirement conditions include that the uplink transmission rate of the predicted result is greater than or equal to the standard uplink transmission rate, and the downlink transmission rate of the predicted result is greater than or equal to the standard downlink transmission rate, and the latency of the predicted result is less than or equal to the standard latency, and the reliability of the predicted result is greater than or equal to the standard reliability.

6. The method according to claim 5, characterized in that, Determining the target carrier from the first carrier and the second carrier based on the satisfaction score of the first carrier and the satisfaction score of the second carrier includes: In response to the fact that the satisfaction score of the first carrier is greater than or equal to the satisfaction score of the second carrier, the first carrier is determined as the target carrier; In response to the fact that the satisfaction score of the first carrier is less than the satisfaction score of the second carrier, the second carrier is determined as the target carrier.

7. The method according to claim 5, characterized in that, The process of determining the satisfaction score of the first carrier includes: Based on the uplink transmission rate of the first prediction result and the standard uplink transmission rate of the standard transmission performance parameter, a first score of the first carrier is determined. The first score of the first carrier is used to characterize the degree of conformity between the uplink transmission rate of the first carrier and the standard uplink transmission rate of the standard transmission performance parameter. Based on the downlink transmission rate of the first prediction result and the standard downlink transmission rate of the standard transmission performance parameter, a second score of the first carrier is determined. The second score of the first carrier is used to characterize the degree of conformity between the downlink transmission rate of the first carrier and the standard downlink transmission rate of the standard transmission performance parameter. Based on the standard delay of the standard transmission performance parameters and the delay of the first prediction result, a third score of the first carrier is determined. The third score of the first carrier is used to characterize the degree of conformity between the delay of the first carrier and the standard delay of the standard transmission performance parameters. Based on the reliability of the first prediction result and the standard reliability of the standard transmission performance parameters, a fourth score for the first carrier is determined. The fourth score of the first carrier is used to characterize the degree of conformity between the reliability of the first carrier and the standard reliability of the standard transmission performance parameters. Based on the first score, the second score, the third score, and the fourth score of the first carrier, the satisfaction score of the first carrier is determined.

8. The method according to claim 5, characterized in that, The process of determining the satisfaction score of the second carrier includes: Based on the uplink transmission rate of the second prediction result and the standard uplink transmission rate of the standard transmission performance parameter, a first score of the second carrier is determined. The first score of the second carrier is used to characterize the degree of conformity between the uplink transmission rate of the second carrier and the standard uplink transmission rate of the standard transmission performance parameter. Based on the downlink transmission rate of the second prediction result and the standard downlink transmission rate of the standard transmission performance parameter, a second score of the second carrier is determined. The second score of the second carrier is used to characterize the degree of conformity between the downlink transmission rate of the second carrier and the standard downlink transmission rate of the standard transmission performance parameter. Based on the standard delay of the standard transmission performance parameters and the delay of the second prediction result, a third score of the second carrier is determined. The third score of the second carrier is used to characterize the degree of conformity between the delay of the second carrier and the standard delay of the standard transmission performance parameters. Based on the reliability of the second prediction result and the standard reliability of the standard transmission performance parameters, a fourth score for the second carrier is determined. The fourth score of the second carrier is used to characterize the degree of conformity between the reliability of the second carrier and the standard reliability of the standard transmission performance parameters. Based on the first score, the second score, the third score, and the fourth score of the second carrier, the satisfaction score of the second carrier is determined.

9. The method according to claim 1, characterized in that, The determination of the first prediction result based on terminal state parameters and network performance parameters of the first carrier includes: The terminal state parameters and the network performance parameters of the first carrier are processed by the pre-trained first gradient boosting decision tree GSDT model to obtain the first prediction result; The determination of the second prediction result based on the terminal state parameters and the network performance parameters of the second carrier includes: The terminal state parameters and the network performance parameters of the second carrier are processed by a pre-trained second gradient boosting decision tree (GSDT) model to obtain the second prediction result.

10. A carrier wave determination device, characterized in that, The device includes: The first determining unit is used to determine the target service type corresponding to the service data of the terminal. The second determining unit is used to determine a first prediction result based on terminal state parameters and network performance parameters of the first carrier. The terminal state parameters are used to indicate the channel state and mobility state of the terminal, and the first prediction result is used to indicate the transmission performance that can be achieved when transmitting service data of the target service type on the first carrier. The third determining unit is used to determine a second prediction result based on the terminal status parameters and the network performance parameters of the second carrier. The second prediction result is used to indicate the transmission performance that can be achieved when transmitting service data of the target service type on the second carrier. The fourth determining unit is used to determine the target carrier from the first carrier and the second carrier based on the first prediction result and the second prediction result; The frequency of the first carrier is different from the frequency of the second carrier.

11. An electronic device, characterized in that, include: A processor and a communication interface; the communication interface is coupled to the processor, the processor being configured to run computer programs or instructions to implement the carrier determination method as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed by a computer, perform the carrier determination method as described in any one of claims 1-9.

13. A computer program product, characterized in that, The computer program product includes computer instructions that, when executed on a computer, cause the computer to perform the carrier determination method as described in any one of claims 1-9.